Voice review analysis

Abstract

Systems and methods for Artificial Intelligence (AI)-based analysis of oral reviews are provided. An example method includes prompting a user to provide an oral review concerning a subject; providing the user with an interface configured to receive the oral review; receiving, via the interface, the oral review concerning the subject in a free format; generating, based on the oral review, a text for review and presenting the text for review to the user; and providing, to the user, an option to publish the text for review via at least one social media. Generating the text for review may include removing filler words from the oral review and converting the oral review from the free format to a format according to a grammar rule of at least one human language.

What is claimed is: 
     
       1. A method for Artificial Intelligence (AI)-based analysis of oral reviews, the method comprising:
 prompting a user to provide an oral review concerning a subject; 
 providing the user with an interface configured to receive the oral review; 
 upon providing the interface, activating an acoustic sensor associated with a user device, the user device being associated with the user; 
 upon the activation of the acoustic sensor, analyzing an ambient acoustic signal to detect presence of a voice of the user; 
 in response to the detection, recording, via the acoustic sensor, the ambient acoustic signal to receive, via the interface, the oral review concerning the subject in a free format; 
 generating, based on the oral review, a text for review; 
 presenting the text for review to the user; 
 providing, to the user, an option to publish the text for review via at least one social media; 
 determining that the oral review includes more than a predetermined number of keywords inconsistent with the subject; and 
 notifying a service provider or a product provider that the oral review includes a message inconsistent with the subject. 
 
     
     
       2. The method of  claim 1 , further comprising analyzing the oral review with the AI to determine that the user has expressed a positive opinion regarding the subject, wherein the determining includes one of the following:
 determining, based on the voice of the user, that an emotional state of the user is positive; and 
 determining that the user has uttered one or more of predetermined keywords. 
 
     
     
       3. The method of  claim 1 , wherein the generating, based on the oral review, the text for review includes:
 generating, based on the oral review, an intermediate text matching words that the user has uttered during the oral review; and 
 analyzing the intermediate text to generate the text for review. 
 
     
     
       4. The method of  claim 3 , wherein the analyzing the intermediate text includes one or more of the following:
 removing filler words from the intermediate text; and 
 converting the intermediate text from the free format to a format according to a grammar rule of at least one human language. 
 
     
     
       5. The method of  claim 1 , further comprising:
 analyzing the oral review with the AI to determine that the user has expressed a negative opinion regarding the subject; and 
 in response to the determination, sending a report concerning the negative opinion to the service provider or the product provider. 
 
     
     
       6. The method of  claim 5 , further comprising presenting information to facilitate the user to contact the service provider or the product provider. 
     
     
       7. The method of  claim 1 , further comprising:
 analyzing the oral review with the AI based on predetermined parameters to determine that the oral review includes a fraudulent message, wherein the analyzing includes determining that the oral review includes a first part and a second part contradicting to the first part; 
 in response to the determination, notifying the service provider or the product provider of the fraudulent message. 
 
     
     
       8. The method of  claim 7 , wherein the determination that the oral review includes the fraudulent message includes
 determining, based on a speech of the user, that a speed of the speech differs from a predetermined speed. 
 
     
     
       9. The method of  claim 1 , wherein:
 the subject includes one of the following: a product, a service, and a policy; and 
 the oral review is initiated via one or more of the following: a link, a text message, a Quick Response (QR) code printed on the product, and a voice prompt. 
 
     
     
       10. A system for Artificial Intelligence (AI)-based analysis of oral reviews, the system comprising:
 a processor; and 
 a memory storing instructions that, when executed by the processor, configure the processor to:
 prompt a user to provide an oral review concerning a subject; 
 provide the user with an interface configured to receive the oral review; 
 upon providing the interface, activate an acoustic sensor associated with a user device, the user device being associated with the user; 
 upon the activation of the acoustic sensor, analyze an ambient acoustic signal to detect presence of a voice of the user; 
 in response to the detection, record, via the acoustic sensor, the ambient acoustic signal to receive, via the interface, the oral review concerning the subject in a free format; 
 generate, based on the oral review, a text for review; 
 present the text for review to the user; 
 provide, to the user, an option to publish the text for review via at least one social media; 
 determine that the oral review includes more than a predetermined number of keywords inconsistent with the subject; and 
 notify a service provider or a product provider that the oral review includes a message inconsistent with the subject. 
 
 
     
     
       11. The system of  claim 10 , wherein the processor is further configured to analyze the oral review with the AI to determine that the user has expressed a positive opinion regarding the subject, wherein the determining includes one of the following:
 determining, based on the voice of the user, that an emotional state of the user is positive; and 
 determining that the user has uttered one or more of predetermined keywords. 
 
     
     
       12. The system of  claim 10 , wherein the generating, based on the oral review, the text for review includes:
 generating, based on the oral review, an intermediate text matching words that the user has uttered during the oral review; and 
 analyzing the intermediate text to generate the text for review. 
 
     
     
       13. The system of  claim 12 , wherein the analyzing the intermediate text includes one or more of the following:
 removing filler words from the intermediate text; and 
 converting the intermediate text from the free format to a format according to a grammar rule of at least one human language. 
 
     
     
       14. The system of  claim 10 , wherein the processor is further configured to:
 analyze the oral review with the AI to determine that the user has expressed a negative opinion regarding the subject; and 
 in response to the determination, send a report concerning the negative opinion to the service provider or the product provider. 
 
     
     
       15. The system of  claim 14 , wherein the processor is further configured to present information to facilitate the user to contact the service provider or the product provider. 
     
     
       16. The system of  claim 10 , wherein the processor is further configured to:
 analyze the oral review with the AI based on predetermined parameters to determine that the oral review includes a fraudulent message, wherein the analyzing includes determining that the oral review includes a first part and a second part contradicting to the first part; 
 in response to the determination, notify the service provider or the product provider of the fraudulent message. 
 
     
     
       17. The system of  claim 16 , wherein the determination that the oral review includes the fraudulent message includes
 determining, based on a speech of the user, that a speed of the speech differs from a predetermined speed. 
 
     
     
       18. A non-transitory computer-readable storage medium having instructions stored thereon, which, when executed by one or more processors, cause the one or more processors to:
 prompt a user to provide an oral review concerning a subject; 
 provide the user with an interface configured to receive the oral review; 
 upon providing the interface, activate an acoustic sensor associated with a user device, the user device being associated with the user; 
 upon the activation of the acoustic sensor, analyze an ambient acoustic signal to detect presence of a voice of the user; 
 in response to the detection, record, via the acoustic sensor, the ambient acoustic signal to receive, via the interface, the oral review concerning the subject in a free format; 
 generate, based on the oral review, a text for review; 
 present the text for review to the user; 
 provide, to the user, an option to publish the text for review via at least one social media; 
 determine that the oral review includes more than a predetermined number of keywords inconsistent with the subject; and 
 notify a service provider or a product provider that the oral review includes a message inconsistent with the subject.